[CTGAN] CTGAN

Author

신록예찬

Published

July 19, 2023

!conda env list

# conda environments:
#
base                     /home/coco/anaconda3
py38                  *  /home/coco/anaconda3/envs/py38

- Ref: https://github.com/sdv-dev/CTGAN

from ctgan import CTGAN
from ctgan import load_demo

"""Demo module."""

import pandas as pd

DEMO_URL = 'http://ctgan-demo.s3.amazonaws.com/census.csv.gz'


def load_demo():
    """Load the demo."""
    return pd.read_csv(DEMO_URL, compression='gzip')

load_demo()

	age	workclass	fnlwgt	education	education-num	marital-status	occupation	relationship	race	sex	capital-gain	capital-loss	hours-per-week	native-country	income
0	39	State-gov	77516	Bachelors	13	Never-married	Adm-clerical	Not-in-family	White	Male	2174	0	40	United-States	<=50K
1	50	Self-emp-not-inc	83311	Bachelors	13	Married-civ-spouse	Exec-managerial	Husband	White	Male	0	0	13	United-States	<=50K
2	38	Private	215646	HS-grad	9	Divorced	Handlers-cleaners	Not-in-family	White	Male	0	0	40	United-States	<=50K
3	53	Private	234721	11th	7	Married-civ-spouse	Handlers-cleaners	Husband	Black	Male	0	0	40	United-States	<=50K
4	28	Private	338409	Bachelors	13	Married-civ-spouse	Prof-specialty	Wife	Black	Female	0	0	40	Cuba	<=50K
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
32556	27	Private	257302	Assoc-acdm	12	Married-civ-spouse	Tech-support	Wife	White	Female	0	0	38	United-States	<=50K
32557	40	Private	154374	HS-grad	9	Married-civ-spouse	Machine-op-inspct	Husband	White	Male	0	0	40	United-States	>50K
32558	58	Private	151910	HS-grad	9	Widowed	Adm-clerical	Unmarried	White	Female	0	0	40	United-States	<=50K
32559	22	Private	201490	HS-grad	9	Never-married	Adm-clerical	Own-child	White	Male	0	0	20	United-States	<=50K
32560	52	Self-emp-inc	287927	HS-grad	9	Married-civ-spouse	Exec-managerial	Wife	White	Female	15024	0	40	United-States	>50K

32561 rows × 15 columns

real_data = load_demo()

# Names of the columns that are discrete
discrete_columns = [
    'workclass',
    'education',
    'marital-status',
    'occupation',
    'relationship',
    'race',
    'sex',
    'native-country',
    'income'
]

ctgan = CTGAN(epochs=10)
ctgan.fit(real_data, discrete_columns)

# Create synthetic data
synthetic_data = ctgan.sample(1000)

Exception ignored on calling ctypes callback function: <function _ThreadpoolInfo._find_modules_with_dl_iterate_phdr.<locals>.match_module_callback at 0x7fd20e2df430>
Traceback (most recent call last):
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 400, in match_module_callback
    self._make_module_from_path(filepath)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 515, in _make_module_from_path
    module = module_class(filepath, prefix, user_api, internal_api)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 606, in __init__
    self.version = self.get_version()
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 646, in get_version
    config = get_config().split()
AttributeError: 'NoneType' object has no attribute 'split'
Exception ignored on calling ctypes callback function: <function _ThreadpoolInfo._find_modules_with_dl_iterate_phdr.<locals>.match_module_callback at 0x7fd2b8692550>
Traceback (most recent call last):
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 400, in match_module_callback
    self._make_module_from_path(filepath)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 515, in _make_module_from_path
    module = module_class(filepath, prefix, user_api, internal_api)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 606, in __init__
    self.version = self.get_version()
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 646, in get_version
    config = get_config().split()
AttributeError: 'NoneType' object has no attribute 'split'
Exception ignored on calling ctypes callback function: <function _ThreadpoolInfo._find_modules_with_dl_iterate_phdr.<locals>.match_module_callback at 0x7fd20df09f70>
Traceback (most recent call last):
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 400, in match_module_callback
    self._make_module_from_path(filepath)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 515, in _make_module_from_path
    module = module_class(filepath, prefix, user_api, internal_api)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 606, in __init__
    self.version = self.get_version()
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 646, in get_version
    config = get_config().split()
AttributeError: 'NoneType' object has no attribute 'split'
Exception ignored on calling ctypes callback function: <function _ThreadpoolInfo._find_modules_with_dl_iterate_phdr.<locals>.match_module_callback at 0x7fd20e2df430>
Traceback (most recent call last):
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 400, in match_module_callback
    self._make_module_from_path(filepath)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 515, in _make_module_from_path
    module = module_class(filepath, prefix, user_api, internal_api)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 606, in __init__
    self.version = self.get_version()
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 646, in get_version
    config = get_config().split()
AttributeError: 'NoneType' object has no attribute 'split'
Exception ignored on calling ctypes callback function: <function _ThreadpoolInfo._find_modules_with_dl_iterate_phdr.<locals>.match_module_callback at 0x7fd20df09f70>
Traceback (most recent call last):
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 400, in match_module_callback
    self._make_module_from_path(filepath)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 515, in _make_module_from_path
    module = module_class(filepath, prefix, user_api, internal_api)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 606, in __init__
    self.version = self.get_version()
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 646, in get_version
    config = get_config().split()
AttributeError: 'NoneType' object has no attribute 'split'
Exception ignored on calling ctypes callback function: <function _ThreadpoolInfo._find_modules_with_dl_iterate_phdr.<locals>.match_module_callback at 0x7fd20df09c10>
Traceback (most recent call last):
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 400, in match_module_callback
    self._make_module_from_path(filepath)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 515, in _make_module_from_path
    module = module_class(filepath, prefix, user_api, internal_api)
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 606, in __init__
    self.version = self.get_version()
  File "/home/coco/anaconda3/envs/py38/lib/python3.8/site-packages/threadpoolctl.py", line 646, in get_version
    config = get_config().split()
AttributeError: 'NoneType' object has no attribute 'split'

- 실제자료

real_data

	age	workclass	fnlwgt	education	education-num	marital-status	occupation	relationship	race	sex	capital-gain	capital-loss	hours-per-week	native-country	income
0	39	State-gov	77516	Bachelors	13	Never-married	Adm-clerical	Not-in-family	White	Male	2174	0	40	United-States	<=50K
1	50	Self-emp-not-inc	83311	Bachelors	13	Married-civ-spouse	Exec-managerial	Husband	White	Male	0	0	13	United-States	<=50K
2	38	Private	215646	HS-grad	9	Divorced	Handlers-cleaners	Not-in-family	White	Male	0	0	40	United-States	<=50K
3	53	Private	234721	11th	7	Married-civ-spouse	Handlers-cleaners	Husband	Black	Male	0	0	40	United-States	<=50K
4	28	Private	338409	Bachelors	13	Married-civ-spouse	Prof-specialty	Wife	Black	Female	0	0	40	Cuba	<=50K
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
32556	27	Private	257302	Assoc-acdm	12	Married-civ-spouse	Tech-support	Wife	White	Female	0	0	38	United-States	<=50K
32557	40	Private	154374	HS-grad	9	Married-civ-spouse	Machine-op-inspct	Husband	White	Male	0	0	40	United-States	>50K
32558	58	Private	151910	HS-grad	9	Widowed	Adm-clerical	Unmarried	White	Female	0	0	40	United-States	<=50K
32559	22	Private	201490	HS-grad	9	Never-married	Adm-clerical	Own-child	White	Male	0	0	20	United-States	<=50K
32560	52	Self-emp-inc	287927	HS-grad	9	Married-civ-spouse	Exec-managerial	Wife	White	Female	15024	0	40	United-States	>50K

32561 rows × 15 columns

- 합성된자료

synthetic_data

	age	workclass	fnlwgt	education	education-num	marital-status	occupation	relationship	race	sex	capital-gain	capital-loss	hours-per-week	native-country	income
0	19	Self-emp-inc	167797	HS-grad	9	Never-married	Armed-Forces	Husband	White	Male	111	-1	40	United-States	<=50K
1	31	Private	66993	Some-college	9	Divorced	Sales	Not-in-family	Asian-Pac-Islander	Male	88	-4	40	United-States	<=50K
2	40	Federal-gov	129625	Bachelors	9	Married-civ-spouse	Adm-clerical	Other-relative	White	Female	-7	-1	67	United-States	<=50K
3	20	Private	174876	Bachelors	14	Married-civ-spouse	Prof-specialty	Husband	White	Male	27	-7	19	United-States	<=50K
4	53	Private	36484	Masters	16	Widowed	Prof-specialty	Not-in-family	White	Female	13	0	30	United-States	>50K
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
995	42	Private	255160	HS-grad	14	Never-married	Adm-clerical	Not-in-family	Black	Female	29	3	47	United-States	<=50K
996	38	Self-emp-inc	149788	HS-grad	9	Never-married	Adm-clerical	Husband	White	Male	106	-6	40	United-States	<=50K
997	44	State-gov	163575	HS-grad	9	Married-civ-spouse	?	Unmarried	Amer-Indian-Eskimo	Female	-4	4	52	France	<=50K
998	20	Self-emp-not-inc	135323	Some-college	9	Married-civ-spouse	Tech-support	Husband	White	Male	-48	-4	40	Philippines	<=50K
999	40	Private	218873	10th	11	Never-married	Exec-managerial	Husband	Asian-Pac-Islander	Female	67	-3	40	United-States	<=50K

1000 rows × 15 columns

Other Formats